Developing the Foundations of Reinforcment Learning
"In reinforcement learning, the feedback you get is either a reward or a penalty, rather than instructions about what you should have done."
Leah Hoffmann
Advertisement
Author Archives
"LLMs might get it sort of right some of the time, but nowhere near as reliably as the average person."
Matarić would like machines to provide social, emotional, and psychological support to people, which makes accessibility a large, unsolved problem.
"We’ve been doing a lot more work with the cloud, because not every clinic or hospital is going to own a supercomputer."
Specifying the Power and Limitations of Randomness
Avi Wigderson, the 2023 ACM A.M. Turing Award laureate, has made lasting contributions to the theory of computational complexity.
Yael Tauman Kalai on her career, proof systems, and certifying correctness.
Achievement in Microarchitecture
David Papworth, a 30-year veteran of Intel, on what led to the P6 microprocessor and how that changed the microarchitectural paradigm.
2023-2024 ACM Athena Lecturer Margo Seltzer recalls the motivations behind the development of the Berkeley DB database software library, and other achievements during her career.
How Many Ways Can You Teach a Robot?
ACM Prize recipient Pieter Abbeel is working to help robots learn, and learn to improve.
Bob Metcalfe, who co-invented Ethernet networking technology, continues to take on new challenges as a computational engineer.
Shape the Future of Computing
ACM encourages its members to take a direct hand in shaping the future of the association. There are more ways than ever to get involved.
Get Involved